next up previous contents
Next: Curve-Like SetsComplexity, Up: Computer Vision Previous: Face Detection and

Fast Image Segmentation Using Stereo Vision

Binocular stereo vision is a biologically motivated approach that uses two slightly different views of a scene to extract information about its three-dimensional properties. The two underlying principles of our approach to stereopsis are parallel computation of binocular disparity and the use of the resulting disparity map for image segmentation. The method divides the two images of the stereo pair into small sections and obtains initial estimations for the disparities of all such sections. The division of the image pair is motivated by data representation in the ocular dominance columns of the primary visual cortex where information from the left and right eyes are represented in the form of interlacing image ``patches''. The algorithm uses the cepstrum, a method traditionally used in echo detection and provides a local estimation of binocular disparity between corresponding patches. First the properties of cepstrum are used to offer improvements to the initial disparity estimation stage. Second the knowledge of the performance of cepstrum is used to provide an interpretation of the initial disparity map and motivate a method for its refinement. In the next stage, we refine the initial disparity estimations using neighbouring disparity information. We employ a modified median filtering scheme for the refinement stage. Finally, based on the methods used in the disparity estimation and refinement stages, we illustrate that the overall disparity map is suitable for figure-ground separation. We provide evidence for the plausibility of the disparity estimation algorithm and the properties of the overall disparity map in the context of biological stereopsis. The algorithm is implemented on a network of TMS320C40 processors and is intended for use with autonomous mobile robots. The processing time is approximately 0.8 seconds for a 128 [{_inline}$times${_inline}] 128 image which, to our knowledge, is faster than all available stereo algorithms.

M. Ezzati, M.D. Levine



next up previous contents
Next: Curve-Like SetsComplexity, Up: Computer Vision Previous: Face Detection and



Thierry Baron
Mon Nov 13 10:43:02 EST 1995